
MCP Finnhub Server
Provides comprehensive financial market data and news through the Finnhub API. Enables real-time stock quotes, company profiles, financial metrics, analyst recommendations, and market news access.
README
MCP Finnhub Server
A comprehensive financial market data and news service powered by the Finnhub API. This MCP server provides real-time stock quotes, company profiles, financial metrics, analyst recommendations, and market news.
Features
- get_market_news: Get latest market news by category (general, forex, crypto, merger)
- get_stock_quote: Get real-time stock quotes with pricing and trading data
- get_company_profile: Get detailed company information and profiles
- get_basic_financials: Get key financial metrics and ratios
- get_recommendation_trends: Get analyst recommendation trends and ratings
MCP Protocol Endpoints
GET /health
- Health check endpointPOST /mcp
- Main MCP protocol endpoint for all tool interactions- Available tools accessible via MCP protocol:
get_market_news
- Get latest market news by categoryget_stock_quote
- Get real-time stock quotesget_company_profile
- Get detailed company informationget_basic_financials
- Get key financial metrics and ratiosget_recommendation_trends
- Get analyst recommendation trends
Configuration
Required Environment Variables
FINNHUB_API_KEY
- Your Finnhub API key (get one free at finnhub.io)
Optional Environment Variables
PORT
- Server port (default: 8000)HOST
- Server host (default: 0.0.0.0)
Development
Requirements
- Python 3.13+
- FastMCP 2.11.2+
- uv (for dependency management)
- Finnhub API key
Setup
# Install dependencies
uv sync
# Set your API key
export FINNHUB_API_KEY="your_api_key_here"
# Run tests with proper async support
uv run pytest
# Run server locally (streamable-http transport)
uv run python server.py
The server will start on http://localhost:8000
using the streamable-http transport. All tool interactions must go through the MCP protocol endpoint at /mcp
.
Docker Build & Push
Use the provided Makefile for common tasks:
# Run tests
make test
# Build Docker image
make build
# Push to registry (requires Docker Hub login)
make push
# Test, build, and push
make all
# Interactive version release
make release
Manual Docker commands:
# Build image
docker build -t nimbletools/mcp-finnhub .
# Run container with API key
docker run -e FINNHUB_API_KEY="your_api_key" -p 8000:8000 nimbletools/mcp-finnhub
# Push to Docker Hub
docker push nimbletools/mcp-finnhub
Usage Examples
All tool interactions must use the MCP protocol. Here are examples of proper MCP requests:
Initialize MCP Session
First, establish an MCP session to initialize the connection:
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {},
"clientInfo": {
"name": "test-client",
"version": "1.0.0"
}
}
}'
List Available Tools
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list"
}'
Get Market News
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "get_market_news",
"arguments": {
"category": "general"
}
}
}'
Get Stock Quote
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 4,
"method": "tools/call",
"params": {
"name": "get_stock_quote",
"arguments": {
"symbol": "AAPL"
}
}
}'
Get Company Profile
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 5,
"method": "tools/call",
"params": {
"name": "get_company_profile",
"arguments": {
"symbol": "MSFT"
}
}
}'
Note: Session management is required. You must initialize the MCP session before making tool calls. Each request should use unique id
values to track responses properly.
Finnhub API
This server uses the Finnhub API to provide financial data. You'll need a free API key to use this service.
Free Tier Limits
- 60 API calls/minute
- Basic stock data, news, and company information
- Real-time US stock prices
Premium Features
- Higher rate limits
- More historical data
- Advanced financial metrics
- Global market coverage
About
Part of the NimbleTools ecosystem. From the makers of NimbleBrain.
License
MIT License - see LICENSE for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.